© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 7542
    Prev
    Next
    INDEX
    Explanations

    terms related to singing and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuccessListener
    -0.47
     arşivlendi
    -0.45
     trauma
    -0.44
    مصادر
    -0.43
     useEffect
    -0.42
     Lupin
    -0.42
     autorytatywna
    -0.42
     Verlust
    -0.42
     estekak
    -0.41
     ImportError
    -0.41
    POSITIVE LOGITS
     singing
    2.88
     sing
    2.80
     sings
    2.63
     sang
    2.53
     Singing
    2.47
    singing
    2.42
    Singing
    2.41
     Sing
    2.33
     sung
    2.33
    Sing
    2.27
    Activations Density 0.154%

    No Known Activations